• Corpus ID: 10332827

A computational challenge problem in materials discovery: synthetic problem generator and real-world datasets

  title={A computational challenge problem in materials discovery: synthetic problem generator and real-world datasets},
  author={Ronan Le Bras and Richard Bernstein and J. Gregoire and Santosh K. Suram and Carla P. Gomes and Bart Selman and Robert Bruce van Dover},
  booktitle={AAAI Conference on Artificial Intelligence},
Newly-discovered materials have been central to recent technological advances. They have contributed significantly to breakthroughs in electronics, renewable energy and green buildings, and overall, have promoted the advancement of global human welfare. Yet, only a fraction of all possible materials have been explored. Accelerating the pace of discovery of materials would foster technological innovations, and would potentially address pressing issues in sustainability, such as energy production… 

Figures and Tables from this paper

Phase Mapper: Accelerating Materials Discovery with AI

Phase-Mapper is a solution platform that tightly integrates XRD experimentation, AI problem solving, and human intelligence for interpreting XRD patterns and inferring the crystal structures of the underlying materials, and has been able to interpret previously unsolvable systems of XRD data at the Department of Energy’s Joint Center for Artificial Photosynthesis.

Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery

This work presents Phase-Mapper, a novel AI platform to solve the phase map identification problem that allows humans to interact with both the data and products of AI algorithms, including the incorporation of human feedback to constrain or initialize solutions.

Pattern Decomposition with Complex Combinatorial Constraints: Application to Materials Discovery

CombiFD is introduced, a framework for factor based pattern decomposition that allows the incorporation of a-priori knowledge as constraints, including complex combinatorial constraints, and a new pattern decompositions algorithm, called AMIQO, based on solving a sequence of (mixed-integer) quadratic programs.

Fast classification of small X-ray diffraction datasets using data augmentation and deep neural networks

The sparse-data problem intrinsic to novel materials development is overcome by coupling a supervised machine-learning approach with a physics-based data augmentation strategy and, using this approach, XRD spectrum acquisition and analysis occurs under 5 minutes, with accuracy comparable to human expert labeling.

Fast and interpretable classification of small X-ray diffraction datasets using data augmentation and deep neural networks

The scarce data problem intrinsic to novel materials development is overcome by coupling a supervised machine learning approach with a model-agnostic, physics-informed data augmentation strategy using simulated data from the Inorganic Crystal Structure Database (ICSD) and experimental data.

Automated Phase Mapping with AgileFD and its Application to Light Absorber Discovery in the V-Mn-Nb Oxide System.

AgileFD, an artificial intelligence algorithm that enables rapid phase mapping from a combinatorial library of X-ray diffraction patterns, is developed and demonstrated through investigation of the V-Mn-Nb oxide system where decomposition of eight oxide phases provides the first phase map for this pseudoternary system.

Leveraging Human Insights Into Problem Structure for Scientific Discovery

The field of computer science is undergoing a fundamental change. The big data revolution calls for improved computational methods, beyond the exponential growth of storage or computational capacity.

Perspective: Composition–structure–property mapping in high-throughput experiments: Turning data into knowledge

With their ability to rapidly elucidate composition-structure-property relationships, high-throughput experimental studies have revolutionized how materials are discovered, optimized, and

Unsupervised phase mapping of X-ray diffraction data by nonnegative matrix factorization integrated with custom clustering

A team led by Ichiro Takeuchi from the University of Maryland and Boian Alexandrov from Los Alamos National Laboratory developed a new computational method based on non-negative matrix factorization and cross-correlation analysis, capable of identifying peak-shifted patterns in XRD datasets.

End-to-End Refinement Guided by Pre-trained Prototypical Classifier

I imitation refinement is proposed, a novel approach to refine imperfect input patterns, guided by a pre-trained classifier incorporating prior knowledge from simulated theoretical data, such that the refined patterns imitate the ideal data.



Commentary: The Materials Project: A materials genome approach to accelerating materials innovation

Accelerating the discovery of advanced materials is essential for human welfare and sustainable, clean energy. In this paper, we introduce the Materials Project (www.materialsproject.org), a core

SMT-Aided Combinatorial Materials Discovery

This work describes a novel approach to the phase map identification problem where domain-specific scientific background knowledge about the physical and chemical properties of the materials are integrated into an SMT reasoning framework and shows that it provides accurate and physically meaningful interpretations of the data, even in the presence of artificially added noise.

The high-throughput highway to computational materials design.

A current snapshot of high-throughput computational materials design is provided, and the challenges and opportunities that lie ahead are highlighted.

Rapid identification of structural phases in combinatorial thin-film libraries using x-ray diffraction and non-negative matrix factorization.

The use of NMF is applied to the problem of analyzing hundreds of x-ray microdiffraction patterns from a combinatorial materials library to reduce the arduous task to the much smaller task of identifying only nine microXRD patterns.

Rapid structural mapping of ternary metallic alloy systems using the combinatorial approach and cluster analysis.

The arduous analysis and classification of hundreds of spectra is reduced to a much shorter analysis of only a few spectra in a procedure for the quick identification of structural phases in thin film composition spread experiments.

Constraint Reasoning and Kernel Clustering for Pattern Decomposition with Scaling

This work proposes a Constraint Programming (CP) model which captures the exact problem structure yet fails to scale in the presence of noisy data about the patterns, and employs Machine Learning techniques to decompose the problem into smaller ones based on a global data-driven view.

Combinatorial Synthesis and Evaluation of Functional Inorganic Materials Using Thin-Film Techniques

Novel phases of functional inorganic chemical systems can be efficiently explored using high-throughput thin-film fabrication techniques coupled with rapid characterization schemes. High-throughput

Crowdsourcing Backdoor Identification for Combinatorial Optimization

This work shows how human computation insights can be key to identifying so-called backdoor variables in combinatorial optimization problems, and leverages the complementary strength of human input, based on a visual identification of problem structure, crowdsourcing, and the power of combinatorsial solvers to exploit complex constraints.

High energy x-ray diffraction/x-ray fluorescence spectroscopy for high-throughput analysis of composition spread thin films.

This work presents a technique for simultaneous acquisition of diffraction images and fluorescence spectra on a continuous composition spread thin film using a 60 keV x-ray source, which affords direct comparison of the measured profiles with powder patterns of known phases.